---
license: apache-2.0
base_model:
- Minthy/ToriiGate-v0.3
language:
- en
tags:
- multimodal
- vision
- image-text-to-text
---


**Torii-Gate-v0.3-nf4** is a bnb nf4 quant of [ToriiGate-v0.3](https://huggingface.co/Minthy/ToriiGate-v0.3) which is based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3).

It is designed for captioning of anime arts and aims to achieve a good understading for a very wide range of images, including single/multiple characters, simple or complex scenes, comic or manga, various interactions and lots of highly cultural concepts.
Using booru-tags grounding it can give detailed descriptions with very high accuracy. It can handle NSFW pretty well, being one of the best small/medium-sized open source models at the time of release.

For batch processing you can use [ide-cap-chan](https://github.com/2dameneko/ide-cap-chan)

All other features are inherited from the parent model.